Optimal Rejection Function Meets Character Recognition Tasks
Optimal Rejection Function Meets Character Recognition Tasks
复制标题
DOI：
10.1007/978-3-030-41299-9_14
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Xiaotong Ji;Yuchen Zheng;D. Suehiro;S. Uchida
中科院分区：
文献类型：
--
作者：
Xiaotong Ji;Yuchen Zheng;D. Suehiro;S. Uchida
本文提出了一种利用拒识函数剔除模糊样本的最优拒识方法。该拒绝函数与分类函数一起在拒绝学习（LwR）框架下进行训练。LwR的亮点是：（1）拒绝策略不是启发式的，而是具有来自机器学习理论的强背景，以及（2）可以在不同于用于分类的特征空间的任意特征空间上训练拒绝函数。后者表明我们可以选择一个更适合拒绝的特征空间。虽然过去的研究LwR只集中在其理论方面，我们建议利用LwR的实际模式分类任务。此外，我们建议使用来自不同CNN层的特征进行分类和拒绝。我们广泛的实验notMNIST分类和字符/非字符分类表明，该方法取得了更好的性能比传统的拒绝策略。
In this paper, we propose an optimal rejection method for rejecting ambiguous samples by a rejection function. This rejection function is trained together with a classification function under the framework of Learning-with-Rejection (LwR). The highlights of LwR are: (1) the rejection strategy is not heuristic but has a strong background from a machine learning theory, and (2) the rejection function can be trained on an arbitrary feature space which is different from the feature space for classification. The latter suggests we can choose a feature space which is more suitable for rejection. Although the past research on LwR focused only its theoretical aspect, we propose to utilize LwR for practical pattern classification tasks. Moreover, we propose to use features from different CNN layers for classification and rejection. Our extensive experiments of notMNIST classification and character/non-character classification demonstrate that the proposed method achieves better performance than traditional rejection strategies.